Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D
  Understanding, Generation, and Instruction Following

Ziyu Guo; Renrui Zhang; Xiangyang Zhu; Yiwen Tang; Xianzheng Ma; Jiaming Han; Kexin Chen; Peng Gao; Xianzhi Li; Hongsheng Li; Pheng-Ann Heng

Paper · arXiv 2309.00615

Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following

Ziyu Guo, Renrui Zhang, Xiangyang Zhu, Yiwen Tang, Xianzheng Ma, Jiaming Han, Kexin Chen, Peng Gao, Xianzhi Li, Hongsheng Li, Pheng-Ann Heng

13 upvotesSeptember 1, 2023arXiv 预印本

AI 摘要

Point-Bind aligns 3D point clouds with various modalities using ImageBind, enabling applications like 3D generation and understanding, while Point-LLM enhances pre-trained LLMs for 3D instructions via parameter-efficient techniques.

Point-Bind3D point cloudsmulti-modalityImageBindjoint embedding spaceany-to-3D generation3D embedding arithmetic3D open-world understandingPoint-LLM3D large language modelparameter-efficient fine-tuning

Abstract

We introduce Point-Bind, a 3D multi-modality model aligning point clouds with 2D image, language, audio, and video. Guided by ImageBind, we construct a joint embedding space between 3D and multi-modalities, enabling many promising applications, e.g., any-to-3D generation, 3D embedding arithmetic, and 3D open-world understanding. On top of this, we further present Point-LLM, the first 3D large language model (LLM) following 3D multi-modal instructions. By parameter-efficient fine-tuning techniques, Point-LLM injects the semantics of Point-Bind into pre-trained LLMs, e.g., LLaMA, which requires no 3D instruction data, but exhibits superior 3D and multi-modal question-answering capacity. We hope our work may cast a light on the community for extending 3D point clouds to multi-modality applications. Code is available at https://github.com/ZiyuGuo99/Point-Bind_Point-LLM.